Development of an RGB-GE Data Generation and XAI-Based On-Site Classification System for Differentiating <i>Zizyphus jujuba</i> and <i>Zizyphus mauritiana</i> in Herbal Medicine Applications
Herbal medicines have significant industrial value in East Asia. <i>Zizyphus jujuba</i> Mill. var. spinosa, used in Korea for treating insomnia, is often confused with <i>Zizyphus mauritiana</i> Lam., which has unverified medicinal properties yet is sold at premium prices. Th...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-05-01
|
| Series: | Agriculture |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-0472/15/10/1022 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849327519243698176 |
|---|---|
| author | So Jin Park Hyein Lee Yu-Jin Jeon Da Hyun Woo Ho-Youn Kim Jung-Ok Kim Dae-Hyun Jung |
| author_facet | So Jin Park Hyein Lee Yu-Jin Jeon Da Hyun Woo Ho-Youn Kim Jung-Ok Kim Dae-Hyun Jung |
| author_sort | So Jin Park |
| collection | DOAJ |
| description | Herbal medicines have significant industrial value in East Asia. <i>Zizyphus jujuba</i> Mill. var. spinosa, used in Korea for treating insomnia, is often confused with <i>Zizyphus mauritiana</i> Lam., which has unverified medicinal properties yet is sold at premium prices. This misclassification undermines consumer trust and poses health risks. This study proposes a deep learning-based classification system trained on RGB-GE data, combining grayscale and edge-detected images with RGB inputs to enhance feature extraction while reducing color-dependency. Our method achieves superior generalization while maintaining cost-effectiveness. The system incorporates Grad-CAM for model interpretation and reliability. By comparing accuracy and speed across basicCNN, DenseNet, and InceptionV3 models, we identified an optimal solution for on-site herbal medicine classification, achieving 98.36% accuracy with basicCNN, ensuring reliable quality control. |
| format | Article |
| id | doaj-art-df3bcbcf84d74042bbcf52968eaa729c |
| institution | Kabale University |
| issn | 2077-0472 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agriculture |
| spelling | doaj-art-df3bcbcf84d74042bbcf52968eaa729c2025-08-20T03:47:52ZengMDPI AGAgriculture2077-04722025-05-011510102210.3390/agriculture15101022Development of an RGB-GE Data Generation and XAI-Based On-Site Classification System for Differentiating <i>Zizyphus jujuba</i> and <i>Zizyphus mauritiana</i> in Herbal Medicine ApplicationsSo Jin Park0Hyein Lee1Yu-Jin Jeon2Da Hyun Woo3Ho-Youn Kim4Jung-Ok Kim5Dae-Hyun Jung6Department of Smart Farm Science, Kyung Hee University, Yongin 17104, Republic of KoreaDepartment of Smart Farm Science, Kyung Hee University, Yongin 17104, Republic of KoreaDepartment of Smart Farm Science, Kyung Hee University, Yongin 17104, Republic of KoreaDepartment of Smart Farm Science, Kyung Hee University, Yongin 17104, Republic of KoreaSmart Farm Research Center, Korea Institute of Science and Technology (KIST), Gangneung-si 25451, Republic of KoreaQuality Certification Center, National Institute of Korean Medicine Development (NIKOM), Daegu 41934, Republic of KoreaDepartment of Smart Farm Science, Kyung Hee University, Yongin 17104, Republic of KoreaHerbal medicines have significant industrial value in East Asia. <i>Zizyphus jujuba</i> Mill. var. spinosa, used in Korea for treating insomnia, is often confused with <i>Zizyphus mauritiana</i> Lam., which has unverified medicinal properties yet is sold at premium prices. This misclassification undermines consumer trust and poses health risks. This study proposes a deep learning-based classification system trained on RGB-GE data, combining grayscale and edge-detected images with RGB inputs to enhance feature extraction while reducing color-dependency. Our method achieves superior generalization while maintaining cost-effectiveness. The system incorporates Grad-CAM for model interpretation and reliability. By comparing accuracy and speed across basicCNN, DenseNet, and InceptionV3 models, we identified an optimal solution for on-site herbal medicine classification, achieving 98.36% accuracy with basicCNN, ensuring reliable quality control.https://www.mdpi.com/2077-0472/15/10/1022feature extractionimage processingdeep learning classificationGrad-CAMherbal medicinefield application technology |
| spellingShingle | So Jin Park Hyein Lee Yu-Jin Jeon Da Hyun Woo Ho-Youn Kim Jung-Ok Kim Dae-Hyun Jung Development of an RGB-GE Data Generation and XAI-Based On-Site Classification System for Differentiating <i>Zizyphus jujuba</i> and <i>Zizyphus mauritiana</i> in Herbal Medicine Applications Agriculture feature extraction image processing deep learning classification Grad-CAM herbal medicine field application technology |
| title | Development of an RGB-GE Data Generation and XAI-Based On-Site Classification System for Differentiating <i>Zizyphus jujuba</i> and <i>Zizyphus mauritiana</i> in Herbal Medicine Applications |
| title_full | Development of an RGB-GE Data Generation and XAI-Based On-Site Classification System for Differentiating <i>Zizyphus jujuba</i> and <i>Zizyphus mauritiana</i> in Herbal Medicine Applications |
| title_fullStr | Development of an RGB-GE Data Generation and XAI-Based On-Site Classification System for Differentiating <i>Zizyphus jujuba</i> and <i>Zizyphus mauritiana</i> in Herbal Medicine Applications |
| title_full_unstemmed | Development of an RGB-GE Data Generation and XAI-Based On-Site Classification System for Differentiating <i>Zizyphus jujuba</i> and <i>Zizyphus mauritiana</i> in Herbal Medicine Applications |
| title_short | Development of an RGB-GE Data Generation and XAI-Based On-Site Classification System for Differentiating <i>Zizyphus jujuba</i> and <i>Zizyphus mauritiana</i> in Herbal Medicine Applications |
| title_sort | development of an rgb ge data generation and xai based on site classification system for differentiating i zizyphus jujuba i and i zizyphus mauritiana i in herbal medicine applications |
| topic | feature extraction image processing deep learning classification Grad-CAM herbal medicine field application technology |
| url | https://www.mdpi.com/2077-0472/15/10/1022 |
| work_keys_str_mv | AT sojinpark developmentofanrgbgedatagenerationandxaibasedonsiteclassificationsystemfordifferentiatingizizyphusjujubaiandizizyphusmauritianaiinherbalmedicineapplications AT hyeinlee developmentofanrgbgedatagenerationandxaibasedonsiteclassificationsystemfordifferentiatingizizyphusjujubaiandizizyphusmauritianaiinherbalmedicineapplications AT yujinjeon developmentofanrgbgedatagenerationandxaibasedonsiteclassificationsystemfordifferentiatingizizyphusjujubaiandizizyphusmauritianaiinherbalmedicineapplications AT dahyunwoo developmentofanrgbgedatagenerationandxaibasedonsiteclassificationsystemfordifferentiatingizizyphusjujubaiandizizyphusmauritianaiinherbalmedicineapplications AT hoyounkim developmentofanrgbgedatagenerationandxaibasedonsiteclassificationsystemfordifferentiatingizizyphusjujubaiandizizyphusmauritianaiinherbalmedicineapplications AT jungokkim developmentofanrgbgedatagenerationandxaibasedonsiteclassificationsystemfordifferentiatingizizyphusjujubaiandizizyphusmauritianaiinherbalmedicineapplications AT daehyunjung developmentofanrgbgedatagenerationandxaibasedonsiteclassificationsystemfordifferentiatingizizyphusjujubaiandizizyphusmauritianaiinherbalmedicineapplications |